实现本地 Markdown 清洗评审器

tests/test_reviewer_artifacts.py

@@ -0,0 +1,132 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any, cast
+
+import pytest
+
+from reviewer.server import ReviewArtifactError, ReviewArtifacts
+from tests.reviewer_fixture import create_review_run, read_json, write_json
+
+
+def test_reviewer_returns_full_comparison_and_all_component_stages(tmp_path: Path) -> None:
+    fixture = create_review_run(tmp_path)
+    repository = ReviewArtifacts(fixture["run_directory"])
+
+    run = cast(dict[str, Any], repository.run_summary())
+    comparison = cast(dict[str, Any], repository.document_comparison("paper"))
+    changed = cast(dict[str, Any], repository.component_stage("paper", 0))
+    unchanged = cast(dict[str, Any], repository.component_stage("paper", 1))
+
+    assert run["summary"] == {
+        "document_count": 1,
+        "success_count": 1,
+        "failed_count": 0,
+        "unstable_count": 0,
+        "change_count": 1,
+    }
+    assert run["documents"][0]["source_available"] is True
+    assert comparison["original_markdown"] == fixture["original"]
+    assert comparison["cleaned_markdown"] == fixture["cleaned"]
+    assert comparison["changes"][0]["editor_range"] == {"start": 4, "end": 7}
+    assert changed["before_markdown"] == fixture["original"]
+    assert changed["after_markdown"] == fixture["cleaned"]
+    assert unchanged["before_markdown"] == fixture["cleaned"]
+    assert unchanged["after_markdown"] == fixture["cleaned"]
+    assert unchanged["changes"] == []
+
+
+@pytest.mark.parametrize("status", ["failed", "unstable"])
+def test_non_success_documents_expose_audit_but_no_formal_output(tmp_path: Path, status: str) -> None:
+    fixture = create_review_run(tmp_path, status=status)
+    repository = ReviewArtifacts(fixture["run_directory"])
+
+    comparison = cast(dict[str, Any], repository.document_comparison("paper"))
+
+    assert comparison["original_markdown"] == fixture["original"]
+    assert comparison["cleaned_markdown"] is None
+    if status == "failed":
+        assert comparison["errors"]
+        assert comparison["residual_proposals"] == []
+    else:
+        assert comparison["errors"] == []
+        assert comparison["residual_proposals"]
+    with pytest.raises(ReviewArtifactError, match="success"):
+        repository.component_stage("paper", 0)
+
+
+def test_historical_run_without_locator_reports_unavailable_source(tmp_path: Path) -> None:
+    fixture = create_review_run(tmp_path, with_locator=False)
+    repository = ReviewArtifacts(fixture["run_directory"])
+
+    summary = cast(dict[str, Any], repository.run_summary())
+
+    assert summary["documents"][0]["source_available"] is False
+    assert "review-locator.json" in summary["documents"][0]["availability_error"]
+    comparison = cast(dict[str, Any], repository.document_comparison("paper"))
+    assert comparison["original_markdown"] is None
+    assert comparison["cleaned_markdown"] == fixture["cleaned"]
+    assert comparison["changes"][0]["editor_range"] is None
+    with pytest.raises(ReviewArtifactError, match=r"review-locator\.json"):
+        repository.component_stage("paper", 0)
+
+
+def test_source_hash_change_is_not_silently_displayed(tmp_path: Path) -> None:
+    fixture = create_review_run(tmp_path)
+    repository = ReviewArtifacts(fixture["run_directory"])
+    source_path = fixture["source_path"]
+    assert isinstance(source_path, Path)
+    source_path.write_text("changed\n", encoding="utf-8")
+
+    summary = cast(dict[str, Any], repository.run_summary())
+
+    assert summary["documents"][0]["source_available"] is False
+    assert "哈希" in summary["documents"][0]["availability_error"]
+    comparison = cast(dict[str, Any], repository.document_comparison("paper"))
+    assert comparison["original_markdown"] is None
+    assert comparison["changes"][0]["editor_range"] is None
+    with pytest.raises(ReviewArtifactError, match="哈希"):
+        repository.component_stage("paper", 0)
+
+
+def test_reviewer_rejects_unknown_schema_and_artifact_path_escape(tmp_path: Path) -> None:
+    fixture = create_review_run(tmp_path)
+    manifest_path = fixture["manifest_path"]
+    assert isinstance(manifest_path, Path)
+    manifest = read_json(manifest_path)
+    manifest["schema_version"] = 2
+    write_json(manifest_path, manifest)
+
+    with pytest.raises(ReviewArtifactError) as unknown:
+        ReviewArtifacts(fixture["run_directory"])
+    assert unknown.value.code == "unsupported_schema"
+
+    second = create_review_run(tmp_path / "second")
+    second_manifest_path = second["manifest_path"]
+    assert isinstance(second_manifest_path, Path)
+    second_manifest = read_json(second_manifest_path)
+    second_manifest["documents"][0]["result_path"] = "../outside.json"
+    write_json(second_manifest_path, second_manifest)
+    with pytest.raises(ReviewArtifactError, match="路径"):
+        ReviewArtifacts(second["run_directory"])
+
+
+def test_reviewer_rejects_tampered_snapshot_chain_and_unknown_identity(tmp_path: Path) -> None:
+    fixture = create_review_run(tmp_path)
+    result_path = fixture["result_path"]
+    assert isinstance(result_path, Path)
+    result = read_json(result_path)
+    result["changes"][0]["after_sha256"] = "0" * 64
+    write_json(result_path, result)
+    repository = ReviewArtifacts(fixture["run_directory"])
+
+    with pytest.raises(ReviewArtifactError) as replay_error:
+        repository.document_comparison("paper")
+    assert replay_error.value.code == "untrusted_replay"
+
+    with pytest.raises(ReviewArtifactError) as document_error:
+        repository.document_comparison("missing")
+    assert document_error.value.http_status == 404
+    with pytest.raises(ReviewArtifactError) as component_error:
+        repository.component_stage("paper", 99)
+    assert component_error.value.http_status == 404